A Novel Tissue Identification Framework in Cataract Surgery Using an Integrated Bioimpedance-Based Probe and Machine Learning Algorithms.

OBJECTIVE: The objective of this work was to develop and experimentally validate a bioimpedance-based framework to identify tissues in contact with the surgical instrument during cataract surgery. METHODS: This work introduces an integrated hardware and software solution based on the unique bioimpedance of different intraocular tissues. The developed hardware can be readily integrated with commonly used surgical instruments. The proposed software framework, which encompasses data acquisition and a machine-learning classifier, is fast enough to be deployed in real-time surgical interventions. The experimental protocol included bioimpedance data collected from 31 ex vivo pig eyes targeting four intraocular tissues: Iris, Cornea, Lens, and Vitreous. RESULTS: A classifier based on a support vector machine exhibited an overall accuracy of 91% across all trials. The algorithm provided substantial performance in detecting the intraocular tissues with 100% reliability and 95% sensitivity for the lens, along with 88% reliability and 94% sensitivity for the vitreous. CONCLUSION: The developed impedance-based framework demonstrated successful intraocular tissue identification. SIGNIFICANCE: Clinical implications include the ability to ensure safe operations by detecting posterior capsule rapture with 94% probability and improving surgical efficacy through lens detection with 100% reliability.

Semi-Automated Extraction of Lens Fragments via a Surgical Robot Using Semantic Segmentation of OCT Images with Deep Learning - Experimental Results in ex vivo Animal Model.

The overarching goal of this work is to demonstrate the feasibility of using optical coherence tomography (OCT) to guide a robotic system to extract lens fragments from ex vivo pig eyes. A convolutional neural network (CNN) was developed to semantically segment four intraocular structures (lens material, capsule, cornea, and iris) from OCT images. The neural network was trained on images from ten pig eyes, validated on images from eight different eyes, and tested on images from another ten eyes. This segmentation algorithm was incorporated into the Intraocular Robotic Interventional Surgical System (IRISS) to realize semi-automated detection and extraction of lens material. To demonstrate the system, the semi-automated detection and extraction task was performed on seven separate ex vivo pig eyes. The developed neural network exhibited 78.20% for the validation set and 83.89% for the test set in mean intersection over union metrics. Successful implementation and efficacy of the developed method were confirmed by comparing the preoperative and postoperative OCT volume scans from the seven experiments.